Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19111
    Prev
    Next
    INDEX
    Explanations

    Geometry: lines and planes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adapt
    -0.09
    Swap
    -0.08
     Git
    -0.07
     swap
    -0.07
     consolidation
    -0.07
     entertainment
    -0.07
     responsibility
    -0.07
    -0.07
    .cloudflare
    -0.07
     burden
    -0.07
    POSITIVE LOGITS
     Neither
    0.10
     infinitely
    0.10
     perpendicular
    0.10
     transversal
    0.10
     Gegensatz
    0.10
     empêcher
    0.10
     foli
    0.09
     ray
    0.09
     rays
    0.09
     препят
    0.09
    Activations Density 0.021%

    No Known Activations